{"id":"https://openalex.org/W2295727839","doi":"https://doi.org/10.14778/2824032.2824073","title":"Gobblin","display_name":"Gobblin","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2295727839","doi":"https://doi.org/10.14778/2824032.2824073","mag":"2295727839"},"language":"en","primary_location":{"id":"doi:10.14778/2824032.2824073","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824073","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112108963","display_name":"Lin Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lin Qiao","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599397","display_name":"Yinan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinan Li","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070320402","display_name":"Sahil Takiar","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sahil Takiar","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655689","display_name":"Ziyang Liu","orcid":"https://orcid.org/0000-0002-6350-8894"},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyang Liu","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002335668","display_name":"Narasimha Veeramreddy","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narasimha Veeramreddy","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044739833","display_name":"Min Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Tu","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778404","display_name":"Ying Dai","orcid":"https://orcid.org/0000-0001-7481-6094"},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Dai","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053970014","display_name":"Issac Buenrostro","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Issac Buenrostro","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020006969","display_name":"Kapil Surlaker","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kapil Surlaker","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100891519","display_name":"Shirshanka Das","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirshanka Das","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077339008","display_name":"Chavdar Botev","orcid":null},"institutions":[{"id":"https://openalex.org/I1316064682","display_name":"LinkedIn (United States)","ror":"https://ror.org/02fyxhe35","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I1316064682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chavdar Botev","raw_affiliation_strings":["LinkedIn Inc., Mountain View, CA"],"affiliations":[{"raw_affiliation_string":"LinkedIn Inc., Mountain View, CA","institution_ids":["https://openalex.org/I1316064682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5112108963"],"corresponding_institution_ids":["https://openalex.org/I1316064682"],"apc_list":null,"apc_paid":null,"fwci":3.2049,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92214657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":"12","first_page":"1764","last_page":"1769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063298463821411},{"id":"https://openalex.org/keywords/nosql","display_name":"NoSQL","score":0.552198052406311},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.49553096294403076},{"id":"https://openalex.org/keywords/operability","display_name":"Operability","score":0.47991475462913513},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.454089879989624},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.43053731322288513},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4182434380054474},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4181072413921356},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3427713215351105},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3126872181892395},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.28910428285598755},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.21282848715782166},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1671733558177948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063298463821411},{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.552198052406311},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.49553096294403076},{"id":"https://openalex.org/C126231374","wikidata":"https://www.wikidata.org/wiki/Q1061298","display_name":"Operability","level":2,"score":0.47991475462913513},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.454089879989624},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.43053731322288513},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4182434380054474},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4181072413921356},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3427713215351105},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3126872181892395},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28910428285598755},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.21282848715782166},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1671733558177948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2824032.2824073","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2824032.2824073","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W73088495","https://openalex.org/W192446467","https://openalex.org/W1967344300","https://openalex.org/W2032598973","https://openalex.org/W2069341504","https://openalex.org/W2100542992","https://openalex.org/W2394680079"],"related_works":["https://openalex.org/W1428625627","https://openalex.org/W3118537095","https://openalex.org/W3204998319","https://openalex.org/W2737538696","https://openalex.org/W3215678666","https://openalex.org/W4255087991","https://openalex.org/W2792109275","https://openalex.org/W4233347783","https://openalex.org/W2949069589","https://openalex.org/W2295727839"],"abstract_inverted_index":{"Data":[0],"ingestion":[1,25,86,145],"is":[2],"an":[3,134,156],"essential":[4],"part":[5],"of":[6,16,31,99,121],"companies":[7],"and":[8,12,29,115,125,150,160,167],"organizations":[9],"that":[10,88],"collect":[11],"analyze":[13],"large":[14],"volumes":[15],"data.":[17],"This":[18,132],"paper":[19],"describes":[20],"Gobblin,":[21],"a":[22,83,97,119,138],"generic":[23],"data":[24,43,85,95,122,144],"framework":[26,87,140],"for":[27,66,130],"Hadoop":[28,61],"one":[30],"LinkedIn's":[32],"latest":[33],"open":[34],"source":[35,68],"products.":[36],"At":[37],"LinkedIn":[38],"we":[39],"need":[40],"to":[41,71,77,92,136,141,152,169],"ingest":[42],"from":[44,96,104],"various":[45,72],"sources":[46,123],"such":[47],"as":[48],"relational":[49],"stores,":[50,52],"NoSQL":[51],"streaming":[53],"systems,":[54],"REST":[55],"endpoints,":[56],"filesystems,":[57],"etc.":[58],"into":[59],"our":[60],"clusters.":[62],"Maintaining":[63],"independent":[64],"pipelines":[65],"each":[67],"can":[69,126],"lead":[70],"operational":[73],"problems.":[74],"Gobblin":[75,101,117,163],"aims":[76],"solve":[78],"this":[79],"issue":[80],"by":[81,107],"providing":[82],"centralized":[84],"makes":[89,164],"it":[90,148,165],"easy":[91,149],"support":[93],"ingesting":[94],"variety":[98],"sources.":[100],"distinguishes":[102],"itself":[103],"similar":[105],"frameworks":[106],"focusing":[108],"on":[109],"three":[110],"core":[111],"principles:":[112],"generality,":[113],"extensibility,":[114],"operability.":[116],"supports":[118],"mixture":[120],"out-of-the-box":[124],"be":[127],"easily":[128],"extended":[129],"more.":[131],"enables":[133],"organization":[135],"use":[137],"single":[139],"handle":[142],"different":[143],"needs,":[146],"making":[147],"inexpensive":[151],"operate.":[153],"Moreover,":[154],"with":[155],"end-to-end":[157],"metrics":[158],"collection":[159],"reporting":[161],"module,":[162],"simple":[166],"efficient":[168],"identify":[170],"issues":[171],"in":[172],"production.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
